Michael J. Duncan, Emma L. J. Eyre, Neil Clarke, Abdul Hamid, Yanguo Jing
{"title":"Importance of fundamental movement skills to predict technical skills in youth grassroots soccer: A machine learning approach","authors":"Michael J. Duncan, Emma L. J. Eyre, Neil Clarke, Abdul Hamid, Yanguo Jing","doi":"10.1177/17479541231202015","DOIUrl":null,"url":null,"abstract":"This study determined the contributors to soccer technical skills in grassroots youth soccer players using a machine learning approach. One hundred and sixty-two boys aged 7 to 14 (mean ± SD = 10.5 ± 2.1) years, who were regularly engaged in grassroots soccer undertook assessments of anthropometry and maturity offset (the time from age at peak height velocity (APHV)), fundamental movement skills (FMS), perceived physical competence, and physical fitness and technical soccer skill using the University of Ghent dribbling test. Coaches rated player's overall soccer skills for their age. Statistical analysis was undertaken, using machine learning models to predict technical skills from the other variables. A stepwise recursive feature elimination with a 5-fold cross-validation method was used to eliminate the worst-performing features and both L1 and L2 regularisation were evaluated during the process. Five models (linear, ridge, lasso, random forest, and boosted trees) were then used in a heuristic approach using a small subset of suitable algorithms to achieve a reasonable level of accuracy within a reasonable time frame to make predictions and compare them to a test set to understand the predictive capabilities of the models. Results from the machine learning analysis indicated that the total FMS score (0 to 50) was the most important feature in predicting technical soccer skills followed by coach rating of child skills for their age, years of playing experience and APHV. Using a random forest, technical skills could be predicted with 99% accuracy in boys who play grassroots soccer, with FMS being the most important contributor.","PeriodicalId":47767,"journal":{"name":"International Journal of Sports Science & Coaching","volume":"19 1","pages":"0"},"PeriodicalIF":1.5000,"publicationDate":"2023-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Sports Science & Coaching","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1177/17479541231202015","RegionNum":4,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"HOSPITALITY, LEISURE, SPORT & TOURISM","Score":null,"Total":0}
引用次数: 0
Abstract
This study determined the contributors to soccer technical skills in grassroots youth soccer players using a machine learning approach. One hundred and sixty-two boys aged 7 to 14 (mean ± SD = 10.5 ± 2.1) years, who were regularly engaged in grassroots soccer undertook assessments of anthropometry and maturity offset (the time from age at peak height velocity (APHV)), fundamental movement skills (FMS), perceived physical competence, and physical fitness and technical soccer skill using the University of Ghent dribbling test. Coaches rated player's overall soccer skills for their age. Statistical analysis was undertaken, using machine learning models to predict technical skills from the other variables. A stepwise recursive feature elimination with a 5-fold cross-validation method was used to eliminate the worst-performing features and both L1 and L2 regularisation were evaluated during the process. Five models (linear, ridge, lasso, random forest, and boosted trees) were then used in a heuristic approach using a small subset of suitable algorithms to achieve a reasonable level of accuracy within a reasonable time frame to make predictions and compare them to a test set to understand the predictive capabilities of the models. Results from the machine learning analysis indicated that the total FMS score (0 to 50) was the most important feature in predicting technical soccer skills followed by coach rating of child skills for their age, years of playing experience and APHV. Using a random forest, technical skills could be predicted with 99% accuracy in boys who play grassroots soccer, with FMS being the most important contributor.
期刊介绍:
The International Journal of Sports Science & Coaching is a peer-reviewed, international, academic/professional journal, which aims to bridge the gap between coaching and sports science. The journal will integrate theory and practice in sports science, promote critical reflection of coaching practice, and evaluate commonly accepted beliefs about coaching effectiveness and performance enhancement. Open learning systems will be promoted in which: (a) sports science is made accessible to coaches, translating knowledge into working practice; and (b) the challenges faced by coaches are communicated to sports scientists. The vision of the journal is to support the development of a community in which: (i) sports scientists and coaches respect and learn from each other as they assist athletes to acquire skills by training safely and effectively, thereby enhancing their performance, maximizing their enjoyment of the sporting experience and facilitating character development; and (ii) scientific research is embraced in the quest to uncover, understand and develop the processes involved in sports coaching and elite performance.